摘要：
Dynamic Programming divides the original problem into subproblems, and then complete the whole task by recursively conquering these subproblems. The k 阅读全文
摘要：
Optimal Value Function is how much reward the best policy can get from a state s, which is the best senario given state s. It can be defined as: Value 阅读全文
摘要：
From the last post about MDP, we know the environment consists of 5 basic elements: S:State Space of environment; A:Actions Space that the environment 阅读全文
摘要：
People commonly tend to put much effort on hyperparameter tuning and training while using Tensoflow&Deep Learning. A realistic problem for TF is how t 阅读全文
摘要：
In this post, I will illustrate Markov Property, Markov Reward Process and finally Markov Decision Process, which are fundamental concepts in Reinforc 阅读全文
摘要：
Partitioner: Partitioning and Combining take place between Map and Reduce phases. It is to club the data which should go to the same reducer based on 阅读全文
摘要：
We are now trying to deploy our Deep Learning model onto Google Cloud. It is required to use Google Function to trigger the Deep Learning predictions. 阅读全文
摘要：
In the previous post, we've illustrated how Hadoop MapReduce prepares input for Mappers. Long story short, InputSplit convert physical storaged data i 阅读全文
摘要：
According to Wikipedia MapReduce, there are two ways to illustrate MapReduce. One contains three steps: Map, Shuffle and Reduce; Another one with 5 st 阅读全文
摘要：
Hadoop(1): HDFS Basics Hadoop(2):HDFS Block Management Hadoop(3): Prepare inputs for MapReduce mappers Hadoop(4): How does Mapper work Hadoop(5): Part 阅读全文